Exploring reservoir computing:Implementation via double stochastic nanowire networks

Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.

Lightweight Intrusion Detection Using Reservoir Computing

The blockchain-empowered Internet of Vehicles(IoV)enables various services and achieves data security and privacy,significantly advancing modern vehicle systems.However,the increased frequency of data transmission and complex network connections among nodes also make them more susceptible to adversarial attacks.As a result,an efficient intrusion detection system(IDS)becomes crucial for securing the IoV environment.Existing IDSs based on convolutional neural networks(CNN)often suffer from high training time and storage requirements.In this paper,we propose a lightweight IDS solution to protect IoV against both intra-vehicle and external threats.Our approach achieves superior performance,as demonstrated by key metrics such as accuracy and precision.Specifically,our method achieves accuracy rates ranging from 99.08% to 100% on the Car-Hacking dataset,with a remarkably short training time.

Multi-target ranging using an optical reservoir computing approach in the laterally coupled semiconductor lasers with self-feedback

We utilize three parallel reservoir computers using semiconductor lasers with optical feedback and light injection to model radar probe signals with delays.Three radar probe signals are generated by driving lasers constructed by a threeelement laser array with self-feedback.The response lasers are implemented also by a three-element lase array with both delay-time feedback and optical injection,which are utilized as nonlinear nodes to realize the reservoirs.We show that each delayed radar probe signal can be predicted well and to synchronize with its corresponding trained reservoir,even when parameter mismatches exist between the response laser array and the driving laser array.Based on this,the three synchronous probe signals are utilized for ranging to three targets,respectively,using Hilbert transform.It is demonstrated that the relative errors for ranging can be very small and less than 0.6%.Our findings show that optical reservoir computing provides an effective way for applications of target ranging.

Emerging memristors and applications in reservoir computing

Recently, with the emergence of ChatGPT, the field of artificial intelligence has garnered widespread attention from various sectors of society. Reservoir Computing (RC) is a neuromorphic computing algorithm used to analyze time-series data. Unlike traditional artificial neural networks that require the weight values of all nodes in the trained network, RC only needs to train the readout layer. This makes the training process faster and more efficient, and it has been used in various applications, including speech recognition, image classification, and control systems. Its flexibility and efficiency make it a popular choice for processing large amounts of complex data. A recent research trend is to develop physical RC, which utilizes the nonlinear dynamic and short-term memory properties of physical systems (photonic modules, spintronic devices, memristors, etc.) to construct a fixed random neural network structure for processing input data to reduce computing time and energy. In this paper, we introduced the recent development of memristors and demonstrated the remarkable data processing capability of RC systems based on memristors. Not only do they possess excellent data processing ability comparable to digital RC systems, but they also have lower energy consumption and greater robustness. Finally, we discussed the development prospects and challenges faced by memristors-based RC systems.

A multi-terminal ion-controlled transistor with multifunctionality and wide temporal dynamics for reservoir computing

Reservoir computing(RC)is an energy-efficient computational framework with low training cost and high efficiency in processing spatiotemporal information.The state-of-the-art fully memristor-based hardware RC system suffers from bottlenecks in the computation efficiencies and accuracy due to the limited temporal tunability in the volatile memristor for the reservoir layer and the nonlinearity in the nonvolatile memristor for the readout layer.Additionally,integrating different types of memristors brings fabrication and integration complexities.To overcome the challenges,a multifunctional multi-terminal electrolyte-gated transistor(MTEGT)that combines both electrostatic and electrochemical doping mechanisms is proposed in this work,integrating both widely tunable volatile dynamics with high temporal tunable range of 10^(2) and nonvolatile memory properties with high long-term potentiation/long-term depression(LTP/LTD)linearity into a single device.An ion-controlled physical RC system fully implemented with only one type of MTEGT is constructed for image recognition using the volatile dynamics for the reservoir and nonvolatility for the readout layer.Moreover,an ultralow normalized mean square error of 0.002 is achieved in a time series prediction task.It is believed that the MTEGT would underlie next-generation neuromorphic computing systems with low hardware costs and high computational performance.

In-materio reservoir computing based on nanowire networks:fundamental,progress,and perspective

The reservoir computing(RC)system,known for its ability to seamlessly integrate memory and computing functions,is considered as a promising solution to meet the high demands for time and energy-efficient computing in the current big data landscape,compared with traditional silicon-based computing systems that have a noticeable disadvantage of separate storage and computation.This review focuses on in-materio RC based on nanowire networks(NWs)from the perspective of materials,extending to reservoir devices and applications.The common methods used in preparing nanowires-based reservoirs,including the synthesis of nanowires and the construction of networks,are firstly systematically summarized.The physical principles of memristive and memcapacitive junctions are then explained.Afterwards,the dynamic characteristics of nanowires-based reservoirs and their computing capability,as well as the neuromorphic applications of NWs-based RC systems in recognition,classification,and forecasting tasks,are explicated in detail.Lastly,the current challenges and future opportunities facing NWs-based RC are highlighted,aiming to provide guidance for further research.

Direct laser writing of graphene oxide for ultra-low power consumption memristors in reservoir computing for digital recognition

A memristor is a promising candidate of new electronic synaptic devices for neuromorphic computing.However,conventional memristors often exhibit complex device structures,cumbersome manufacturing processes,and high energy consumption.Graphene-based materials show great potential as the building materials of memristors.With direct laser writing technology,this paper proposes a lateral memristor with reduced graphene oxide(rGO)and Pt as electrodes and graphene oxide(GO)as function material.This Pt/GO/rGO memristor with a facile lateral structure can be easily fabricated and demonstrates an ultra-low energy consumption of 200 nW.Typical synaptic behaviors are successfully emulated.Meanwhile,the Pt/GO/rGO memristor array is applied in the reservoir computing network,performing the digital recognition with a high accuracy of 95.74%.This work provides a simple and low-cost preparation method for the massive production of artificial synapses with low energy consumption,which will greatly facilitate the development of neural network computing hardware platforms.

A review:Photonics devices,architectures,and algorithms for optical neural computing

The explosive growth of data and information has motivated various emerging non-von Neumann computational approaches in the More-than-Moore era.Photonics neuromorphic computing has attracted lots of attention due to the fascinating advantages such as high speed,wide bandwidth,and massive parallelism.Here,we offer a review on the optical neural computing in our research groups at the device and system levels.The photonics neuron and photonics synapse plasticity are presented.In addition,we introduce several optical neural computing architectures and algorithms including photonic spiking neural network,photonic convolutional neural network,photonic matrix computation,photonic reservoir computing,and photonic reinforcement learning.Finally,we summarize the major challenges faced by photonic neuromorphic computing,and propose promising solutions and perspectives.

Analog Optical Computing for Artificial Intelligence

The rapid development of artificial intelligence(AI)facilitates various applications from all areas but also poses great challenges in its hardware implementation in terms of speed and energy because of the explosive growth of data.Optical computing provides a distinctive perspective to address this bottleneck by harnessing the unique properties of photons including broad bandwidth,low latency,and high energy efficiency.In this review,we introduce the latest developments of optical computing for different AI models,including feedforward neural networks,reservoir computing,and spiking neural networks(SNNs).Recent progress in integrated photonic devices,combined with the rise of AI,provides a great opportunity for the renaissance of optical computing in practical applications.This effort requires multidisciplinary efforts from a broad community.This review provides an overview of the state-of-the-art accomplishments in recent years,discusses the availability of current technologies,and points out various remaining challenges in different aspects to push the frontier.We anticipate that the era of large-scale integrated photonics processors will soon arrive for practical AI applications in the form of hybrid optoelectronic frameworks.

Investigation on Dynamics of Echo State Networks

Dynamics is a key issue about understanding recurrent neural networks(RNNs).Because of the complexity,the problem still remains unanswered in spite of many important progresses.Echo state network(ESN)is a simple approach to design RNNs.It is possible to investigate ESNs’dynamics deeply.However,most of dynamic studies have mainly concentrated on the shallow ESNs and seldom of them explain the dynamics of the deep ones.Therefore,this paper investigates the dynamics of four typical ESNs under a unified theoretical framework.These ESNs contain both the shallow versions and the deep ones.This investigation is helpful to clarify the dynamics of ESNs in a general sense.Also,the short-term memory(STM)of different ESNs is analyzed,which is closely related to the dynamics.This analysis is helpful to determine the hyper-parameters of ESNs for given problems.In addition,the problem-solving abilities of ESNs are investigated through modeling two time series tasks.It further explains the influence of the dynamics on ESN’s performance.

Complex network perspective on modelling chaotic systems via machine learning

Recent advances have demonstrated that a machine learning technique known as "reservoir computing" is a significantly effective method for modelling chaotic systems. Going beyond short-term prediction, we show that long-term behaviors of an observed chaotic system are also preserved in the trained reservoir system by virtue of network measurements. Specifically, we find that a broad range of network statistics induced from the trained reservoir system is nearly identical with that of a learned chaotic system of interest. Moreover, we show that network measurements of the trained reservoir system are sensitive to distinct dynamics and can in turn detect the dynamical transitions in complex systems. Our findings further support that rather than dynamical equations, reservoir computing approach in fact provides an alternative way for modelling chaotic systems.

Thin liquid film as an optical nonlinear-nonlocal medium and memory element in integrated optofluidic reservoir computer

Understanding light–matter interaction lies at the core of our ability to harness physical effects and to translate them into new capabilities realized in modern integrated photonics platforms.Here,we present the design and characterization of optofluidic components in an integrated photonics platform and computationally predict a series of physical effects that rely on thermocapillary-driven interaction between waveguide modes and topography changes of optically thin liquid dielectric film.Our results indicate that this coupling introduces substantial self-induced phase change and transmittance change in a single channel waveguide,transmittance through the Bragg grating waveguide,and nonlocal interaction between adjacent waveguides.We then employ the self-induced effects together with the inherent built-in finite relaxation time of the liquid film,to demonstrate that the light-driven deformation can serve as a reservoir computer capable of performing digital and analog tasks,where the gas–liquid interface operates both as a nonlinear actuator and as an optical memory element.

The reservoir learning power across quantum many-body localization transition

Harnessing the quantum computation power of the present noisy-intermediate-size-quantum devices has received tremendous interest in the last few years. Here we study the learning power of a one-dimensional long-range randomly-coupled quantum spin chain, within the framework of reservoir computing. In time sequence learning tasks, we find the system in the quantum many-body localized (MBL) phase holds long-term memory, which can be attributed to the emergent local integrals of motion. On the other hand, MBL phase does not provide sufficient nonlinearity in learning highly-nonlinear time sequences, which we show in a parity check task. This is reversed in the quantum ergodic phase, which provides sufficient nonlinearity but compromises memory capacity. In a complex learning task of Mackey–Glass prediction that requires both sufficient memory capacity and nonlinearity, we find optimal learning performance near the MBL-to-ergodic transition. This leads to a guiding principle of quantum reservoir engineering at the edge of quantum ergodicity reaching optimal learning power for generic complex reservoir learning tasks. Our theoretical finding can be tested with near-term NISQ quantum devices.

An artificial olfactory inference system based on memristive devices

Due to the complexity of real environments,it is hard to detect toxic and harmful gases by sensors.To address such an issue,an artificial olfactory system is promoted,emulating the function of the human nose by means of gas sensors and an inference system.In this work,an artificial olfactory inference system based on memristive devices is developed to classify four gases(ethanol,methane,ethylene,and carbon monoxide)with 10 different concentrations.First,the spike trains converted from signals of the sensor array are inputted to a reservoir computing(RC)system based on volatile memristive devices,which extracts spatiotemporal features;then the features are processed by a classifier based on nonvolatile memristive devices;the output of the classifier indicates the classification result.Moreover,to reduce the device number and the power consumption,three strategies are applied to reduce the extracted features from the RC system.Eventually,the olfactory inference system successfully identifies the gases with a high accuracy of 95%.